ClawHub
Back to skill

Security audit

news-sentiment-analyst

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent financial news sentiment skill that calls the disclosed Finskills API and does not include hidden code, persistence, or local data access.

Before installing, understand that the skill uses your Finskills API key and may send requested tickers, symbols, sectors, or market-news topics to Finskills to retrieve news. Avoid using it for proprietary watchlists or confidential trading research unless that data sharing is acceptable to you.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README describes fetching news by ticker and topic from the Finskills API but does not clearly warn users that their requested symbols, topics, or market questions will be transmitted to an external service. In a finance-focused skill, users may submit sensitive watchlists, research interests, or trading-related queries; silent transmission of that data weakens informed consent and can expose user intent to a third party.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The example triggers are very broad, natural-language financial questions that overlap with ordinary user conversation, which increases the chance the skill is invoked when the user did not specifically intend to use it. In this skill’s context, unintended invocation can lead to external API calls based on user content and generation of market-oriented output without clear user awareness, creating privacy and consent concerns rather than direct code-execution risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation trigger includes the broad phrase "what's happening in the market today?", which can cause the skill to be invoked for generic finance/news queries even when the user did not explicitly request this specific tool. Over-broad invocation increases the chance of unintended external API use and can steer users into automated market-sentiment analysis when a narrower or safer response would have been sufficient.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.